S
Shinichi Shirakawa
Researcher at Yokohama National University
Publications - 86
Citations - 1367
Shinichi Shirakawa is an academic researcher from Yokohama National University. The author has contributed to research in topics: Computer science & Genetic programming. The author has an hindex of 13, co-authored 69 publications receiving 1005 citations. Previous affiliations of Shinichi Shirakawa include University of Tsukuba & Fujitsu.
Papers
More filters
Proceedings ArticleDOI
A genetic programming approach to designing convolutional neural network architectures
TL;DR: This paper attempts to automatically construct CNN architectures for an image classification task based on Cartesian genetic programming (CGP), and shows that the proposed method can be used to automatically find the competitive CNN architecture compared with state-of-the-art models.
Proceedings ArticleDOI
A genetic programming approach to designing convolutional neural network architectures
TL;DR: In the proposed method, the architectures of CNNs are represented by directed acyclic graphs, in which each node represents highly-functional modules such as convolutional blocks and tensor operations and each edge represents the connectivity of layers.
Proceedings ArticleDOI
Evaluation of Speech-to-Gesture Generation Using Bi-Directional LSTM Network
TL;DR: A novel framework to automatically generate natural gesture motions accompanying speech from audio utterances based on a Bi-Directional LSTM Network that regresses a full 3D skeletal pose of a human from perceptual features extracted from the input audio in each time step.
Posted Content
A Genetic Programming Approach to Designing Convolutional Neural Network Architectures
TL;DR: In this article, a CNN architecture based on Cartesian genetic programming (CGP) was proposed to automatically construct CNN architectures for an image classification task, where highly functional modules, such as convolutional blocks and tensor concatenation, were adopted as the node functions in CGP.
Proceedings ArticleDOI
Evolutionary image segmentation based on multiobjective clustering
TL;DR: This paper proposes a method for evolutionary image segmentation based on multiobjective clustering, in which two objectives, overall deviation and edge value, are optimized simultaneously using a multiobjectives evolutionary algorithm.